In [2]:

    

import pandas as pd
import numpy as np
data = pd.read_csv('data/train.csv')


    

In [3]:

    

data.describe()


    

    
Out[3]:






  

    

      

      
Activity
      
D1
      
D2
      
D3
      
D4
      
D5
      
D6
      
D7
      
D8
      
D9
      
...
      
D1767
      
D1768
      
D1769
      
D1770
      
D1771
      
D1772
      
D1773
      
D1774
      
D1775
      
D1776
    
  
  

    

      
count
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
...
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
      
3751.000000
    
    

      
mean
      
0.542255
      
0.076948
      
0.592436
      
0.068142
      
0.038990
      
0.212112
      
0.686653
      
0.274713
      
0.455133
      
0.749517
      
...
      
0.026926
      
0.014663
      
0.013863
      
0.021861
      
0.015196
      
0.016796
      
0.012263
      
0.011730
      
0.020261
      
0.011197
    
    

      
std
      
0.498278
      
0.079989
      
0.105860
      
0.078414
      
0.115885
      
0.102592
      
0.078702
      
0.090017
      
0.162731
      
0.071702
      
...
      
0.161889
      
0.120215
      
0.116938
      
0.146249
      
0.122348
      
0.128522
      
0.110074
      
0.107683
      
0.140911
      
0.105236
    
    

      
min
      
0.000000
      
0.000000
      
0.282128
      
0.000000
      
0.000000
      
0.002630
      
0.137873
      
0.006130
      
0.000000
      
0.275590
      
...
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
    
    

      
25%
      
0.000000
      
0.033300
      
0.517811
      
0.000000
      
0.000000
      
0.138118
      
0.625627
      
0.207374
      
0.378062
      
0.707339
      
...
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
    
    

      
50%
      
1.000000
      
0.066700
      
0.585989
      
0.050000
      
0.000000
      
0.190926
      
0.674037
      
0.277845
      
0.499942
      
0.738961
      
...
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
    
    

      
75%
      
1.000000
      
0.100000
      
0.668395
      
0.100000
      
0.000000
      
0.261726
      
0.740663
      
0.335816
      
0.569962
      
0.788177
      
...
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
    
    

      
max
      
1.000000
      
1.000000
      
0.964381
      
0.950000
      
1.000000
      
1.000000
      
0.994735
      
0.790831
      
0.989870
      
1.000000
      
...
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
    
  

8 rows × 1777 columns

In [21]:

    

y = data.as_matrix(['Activity'])
x = data.as_matrix(['D%i' % d for d in range(1,1777)])
print(y)
print(x)


    

    




[[1]
 [1]
 [1]
 ..., 
 [0]
 [1]
 [0]]
[[ 0.          0.49700901  0.1        ...,  0.          0.          0.        ]
 [ 0.36666667  0.60629148  0.05       ...,  0.          1.          0.        ]
 [ 0.0333      0.48012427  0.         ...,  0.          0.          0.        ]
 ..., 
 [ 0.2         0.52056377  0.         ...,  0.          0.          0.        ]
 [ 0.1         0.7656462   0.         ...,  0.          0.          0.        ]
 [ 0.13333333  0.53395198  0.         ...,  0.          0.          0.        ]]

In [22]:

    

from sklearn.ensemble import RandomForestRegressor
clf = RandomForestRegressor()
clf = clf.fit(x, y)


    

    




/Users/yoshi/.pyenv/versions/anaconda3-2.3.0/lib/python3.4/site-packages/ipykernel/__main__.py:3: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
  app.launch_new_instance()

In [23]:

    

test_data = pd.read_csv('data/test.csv')
test_data = test_data.as_matrix()
result = clf.predict(test_data)


    

In [28]:

    

def writeout(y):
    with open('./result.csv', 'w') as f:
        f.write('MoleculeId,PredictedProbability\n')
        for index, verdict in enumerate(y):
            if verdict > 1:
                verdict = 1
            elif verdict < 0:
                verdict = 0
            f.write('%i,%f\n' % (index+1,verdict))


    

In [32]:

    

from sklearn.ensemble import GradientBoostingRegressor
gbr = GradientBoostingRegressor(n_estimators=5)
gbr = gbr.fit(x, y)


    

    




/Users/yoshi/.pyenv/versions/anaconda3-2.3.0/lib/python3.4/site-packages/sklearn/utils/validation.py:449: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

In [33]:

    

result_boost = gbr.predict(test_data)


    

In [34]:

    

writeout(result_boost)


    

In [ ]: